Generalizable Person Re-Identification by Domain-Invariant Mapping Network

We aim to learn a domain generalizable person re-identification (ReID) model. When such a model is trained on a set of source domains (ReID datasets collected from different camera networks), it can be directly applied to any new unseen dataset for effective ReID without any model updating. Despite its practical value in real-world deployments, generalizable ReID has seldom been studied. In this work, a novel deep ReID model termed Domain-Invariant Mapping Network (DIMN) is proposed. DIMN is designed to learn a mapping between a person image and its identity classifier, i.e., it produces a classifier using a single shot. To make the model domain-invariant, we follow a meta-learning pipeline and sample a subset of source domain training tasks during each training episode. However, the model is significantly different from conventional meta-learning methods in that: (1) no model updating is required for the target domain, (2) different training tasks share a memory bank for maintaining both scalability and discrimination ability, and (3) it can be used to match an arbitrary number of identities in a target domain. Extensive experiments on a newly proposed large-scale ReID domain generalization benchmark show that our DIMN significantly outperforms alternative domain generalization or meta-learning methods.

[1]  Quoc V. Le,et al.  HyperNetworks , 2016, ICLR.

[2]  Bernhard Schölkopf,et al.  Domain Generalization via Invariant Feature Representation , 2013, ICML.

[3]  Gang Wang,et al.  Gated Siamese Convolutional Neural Network Architecture for Human Re-identification , 2016, ECCV.

[4]  Gang Wang,et al.  A Siamese Long Short-Term Memory Architecture for Human Re-identification , 2016, ECCV.

[5]  Qi Tian,et al.  Scalable Person Re-identification on Supervised Smoothed Manifold , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Siddhartha Chaudhuri,et al.  Generalizing Across Domains via Cross-Gradient Training , 2018, ICLR.

[7]  Yi Yang,et al.  Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Joshua Achiam,et al.  On First-Order Meta-Learning Algorithms , 2018, ArXiv.

[9]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Tao Xiang,et al.  The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching , 2017, ArXiv.

[12]  Shaogang Gong,et al.  Associating Groups of People , 2009, BMVC.

[13]  Pong C. Yuen,et al.  Semi-supervised Region Metric Learning for Person Re-identification , 2018, International Journal of Computer Vision.

[14]  Takahiro Okabe,et al.  Hierarchical Gaussian Descriptor for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[16]  Jian Sun,et al.  AlignedReID: Surpassing Human-Level Performance in Person Re-Identification , 2017, ArXiv.

[17]  Yongxin Yang,et al.  Learning to Generalize: Meta-Learning for Domain Generalization , 2017, AAAI.

[18]  Jian-Huang Lai,et al.  Deep Ranking for Person Re-Identification via Joint Representation Learning , 2015, IEEE Transactions on Image Processing.

[19]  Shaogang Gong,et al.  Harmonious Attention Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[21]  Wei Li,et al.  Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Tao Xiang,et al.  Multi-level Factorisation Net for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Anton van den Hengel,et al.  Learning to rank in person re-identification with metric ensembles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[26]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

[27]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Xiaogang Wang,et al.  Locally Aligned Feature Transforms across Views , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

[30]  Kaiqi Huang,et al.  A Multi-Task Deep Network for Person Re-Identification , 2016, AAAI.

[31]  Xiaogang Wang,et al.  End-to-End Deep Learning for Person Search , 2016, ArXiv.

[32]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[33]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[34]  Chang-Tsun Li,et al.  Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification , 2018, BMVC.

[35]  Slawomir Bak,et al.  One-Shot Metric Learning for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Hai Tao,et al.  Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features , 2008, ECCV.

[38]  Liang Wang,et al.  Mask-Guided Contrastive Attention Model for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Yi Yang,et al.  A Discriminatively Learned CNN Embedding for Person Reidentification , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[40]  Yun Fu,et al.  Discriminative Semi-Coupled Projective Dictionary Learning for Low-Resolution Person Re-Identification , 2018, AAAI.

[41]  Shaogang Gong,et al.  International Journal of Computer Vision (The original publication is available at www.springerlink.com) Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding , 2009 .

[42]  Sergey Levine,et al.  Continuous Deep Q-Learning with Model-based Acceleration , 2016, ICML.

[43]  Wei Shen,et al.  Few-Shot Image Recognition by Predicting Parameters from Activations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[44]  Shaogang Gong,et al.  Learning a Discriminative Null Space for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[46]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[47]  Yi Yang,et al.  Generalizing a Person Retrieval Model Hetero- and Homogeneously , 2018, ECCV.

[48]  Alexei A. Efros,et al.  Undoing the Damage of Dataset Bias , 2012, ECCV.

[49]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[50]  Donald A. Adjeroh,et al.  Unified Deep Supervised Domain Adaptation and Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[51]  Yongxin Yang,et al.  Deeper, Broader and Artier Domain Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[52]  Muhittin Gokmen,et al.  Human Semantic Parsing for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[53]  Xiaogang Wang,et al.  Eliminating Background-bias for Robust Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[54]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[55]  Yan Wang,et al.  Resource Aware Person Re-identification Across Multiple Resolutions , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[56]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[58]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[59]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[60]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

[61]  Shaogang Gong,et al.  Person Re-Identification by Deep Joint Learning of Multi-Loss Classification , 2017, IJCAI.

[62]  Longhui Wei,et al.  Person Transfer GAN to Bridge Domain Gap for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.